The limited availability of labelled data in Action Quality Assessment (AQA),
has forced previous works to fine-tune their models pretrained on large-scale
domain-general datasets. This common approach results in weak generalisation,
particularly when there is a significant domain shift. We propose a novel,
parameter efficient, continual pretraining framework, PECoP, to reduce such
domain shift via an additional pretraining stage. In PECoP, we introduce
3D-Adapters, inserted into the pretrained model, to learn spatiotemporal,
in-domain information via self-supervised learning where only the adapter
modules' parameters are updated. We demonstrate PECoP's ability to enhance the
performance of recent state-of-the-art methods (MUSDL, CoRe, and TSA) applied
to AQA, leading to considerable improvements on benchmark datasets, JIGSAWS
($\uparrow6.0\%$), MTL-AQA ($\uparrow0.99\%$), and FineDiving
($\uparrow2.54\%$). We also present a new Parkinson's Disease dataset, PD4T, of
real patients performing four various actions, where we surpass
($\uparrow3.56\%$) the state-of-the-art in comparison. Our code, pretrained
models, and the PD4T dataset are available at this https URL

通过增加额外的预训练阶段，我们引入了 PECoP 这一创新的参数高效的连续预训练框架，并通过自监督学习来减少领域转变对于迁移学习的影响。我们通过 3D 适配器，只更新适配器模块参数的方式，展示了 PECoP 提升最新的 AQA 方法（MUSDL、CoRe 和 TSA）在 JIGSAWS、MTL-AQA 和 FineDiving 基准数据集上的表现，以及超过同类研究的新帕金森病数据集 PD4T 表现（提升 3.56%）。